Qwen2.5 72B Instruct
Alibaba first-party · 131,072 ctx · from $0.36 input / $0.4 output per 1M tokens
- Input price ranks #223 of 447 priced models (cheaper = better).
- Cheaper alternative with ≥ same context: Qwen2.5-VL 7B Instruct at $0.35 input.
- Input price across curated sources ranges $0.36–$1.4 per 1M tokens.
| Provider | Alibaba |
|---|---|
| Family | qwen |
| Context window | 131,072 |
| Max output | 8,192 |
| Input price | $0.36 |
| Output price | $0.4 |
| Cache read | — |
| Cache write | — |
| Reasoning | No |
| Tool calling | Yes |
| Vision | No |
| Open weights | Yes |
| Knowledge cutoff | 2024-04 |
| Released | 2024-09 |
| Last updated | 2024-09 |
Available from 2 curated sources
| Source | Input | Output |
|---|---|---|
| OpenRouter | $0.36 | $0.4 |
| Alibaba first-party | $1.4 | $5.6 |
Identity: Alibaba; data via models.dev + OpenRouter public APIs. Always confirm on the provider's official pricing page.